Bastian Leibe

papers

1,556

total citations

papers (17)

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

ECCV 2020arXiv

citations

From Points to Multi-Object 3D Reconstruction

CVPR 2021arXiv

citations

TarViS: A Unified Approach for Target-Based Video Segmentation

CVPR 2023arXiv

citations

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

ICLR 2024arXiv

citations

3D Segmentation of Humans in Point Clouds with Synthetic Data

ICCV 2023arXiv

citations

HODOR: High-Level Object Descriptors for Object Re-Segmentation in Video Learned From Static Images

CVPR 2022arXiv

citations

Your ViT is Secretly an Image Segmentation Model

CVPR 2025arXiv

citations

DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer

ICCV 2023arXiv

citations

Point-VOS: Pointing Up Video Object Segmentation

CVPR 2024arXiv

citations

Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

CVPR 2025arXiv

citations

DONUT: A Decoder-Only Model for Trajectory Prediction

ICCV 2025arXiv

citations

Bastian Leibe

papers (17)

Siam R-CNN: Visual Tracking by Re-Detection

3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Opening Up Open World Tracking

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

From Points to Multi-Object 3D Reconstruction

TarViS: A Unified Approach for Target-Based Video Segmentation

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

3D Segmentation of Humans in Point Clouds with Synthetic Data

HODOR: High-Level Object Descriptors for Object Re-Segmentation in Video Learned From Static Images

Your ViT is Secretly an Image Segmentation Model

DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer

Point-VOS: Pointing Up Video Object Segmentation

Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

DONUT: A Decoder-Only Model for Trajectory Prediction

papers (17)

Siam R-CNN: Visual Tracking by Re-Detection

3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Opening Up Open World Tracking

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

From Points to Multi-Object 3D Reconstruction

TarViS: A Unified Approach for Target-Based Video Segmentation

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

3D Segmentation of Humans in Point Clouds with Synthetic Data

HODOR: High-Level Object Descriptors for Object Re-Segmentation in Video Learned From Static Images

Your ViT is Secretly an Image Segmentation Model

DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer

Point-VOS: Pointing Up Video Object Segmentation

Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

DONUT: A Decoder-Only Model for Trajectory Prediction